# Don't Parse, Generate! A Sequence to Sequence Architecture for Task-Oriented Semantic Parsing

arXiv: https://arxiv.org/abs/2001.11458 · HTML: https://mlsanity.com/paper/2001.11458/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2020.

## Built on by (most cited first, 30 of 59)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages](https://mlsanity.com/paper/2204.08582/) (2022)
- [Generative Knowledge Graph Construction: A Review](https://mlsanity.com/paper/2210.12714/) (2022)
- [Paradigm Shift in Natural Language Processing](https://mlsanity.com/paper/2109.12575/) (2021)
- [Modern Baselines for SPARQL Semantic Parsing](https://mlsanity.com/paper/2204.12793/) (2022)
- [SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://mlsanity.com/paper/2105.07911/) (2021)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [ReasonBERT: Pre-trained to Reason with Distant Supervision](https://mlsanity.com/paper/2109.04912/) (2021)
- [How much pretraining data do language models need to learn syntax?](https://mlsanity.com/paper/2109.03160/) (2021)
- [CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing](https://mlsanity.com/paper/2210.07074/) (2022)
- [Effective Sequence-to-Sequence Dialogue State Tracking](https://mlsanity.com/paper/2108.13990/) (2021)
- [Intent Classification and Slot Filling for Privacy Policies](https://mlsanity.com/paper/2101.00123/) (2021)
- [Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2104.07275/) (2021)
- [Label Semantic Aware Pre-training for Few-shot Text Classification](https://mlsanity.com/paper/2204.07128/) (2022)
- [Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog](https://mlsanity.com/paper/2104.04923/) (2021)
- [Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data](https://mlsanity.com/paper/2109.04319/) (2021)
- [RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing](https://mlsanity.com/paper/2109.10410/) (2021)
- [A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions](https://mlsanity.com/paper/2308.12700/) (2023)
- [GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understanding](https://mlsanity.com/paper/2204.08325/) (2022)
- [Answer Generation for Retrieval-based Question Answering Systems](https://mlsanity.com/paper/2106.00955/) (2021)
- [KnowGL: Knowledge Generation and Linking from Text](https://mlsanity.com/paper/2210.13952/) (2022)
- [Measuring and Reducing Model Update Regression in Structured Prediction for NLP](https://mlsanity.com/paper/2202.02976/) (2022)
- [Compositional Task-Oriented Parsing as Abstractive Question Answering](https://mlsanity.com/paper/2205.02068/) (2022)
- [Generalists vs. Specialists: Evaluating LLMs on Highly-Constrained Biophysical Sequence Optimization Tasks](https://mlsanity.com/paper/2410.22296/) (2024)
- [Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers](https://mlsanity.com/paper/2109.05186/) (2021)
- [Dialog2API: Task-Oriented Dialogue with API Description and Example Programs](https://mlsanity.com/paper/2212.09946/) (2022)
- [LeafAI: query generator for clinical cohort discovery rivaling a human programmer](https://mlsanity.com/paper/2304.06203/) (2023)
- [El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing](https://mlsanity.com/paper/2101.10524/) (2021)
- [Semantic Parsing in Task-Oriented Dialog with Recursive Insertion-based Encoder](https://mlsanity.com/paper/2109.04500/) (2021)

## Abstract (arXiv)

Virtual assistants such as Amazon Alexa, Apple Siri, and Google Assistant often rely on a semantic parsing component to understand which action(s) to execute for an utterance spoken by its users. Traditionally, rule-based or statistical slot-filling systems have been used to parse "simple" queries; that is, queries that contain a single action and can be decomposed into a set of non-overlapping entities. More recently, shift-reduce parsers have been proposed to process more complex utterances. These methods, while powerful, impose specific limitations on the type of queries that can be parsed; namely, they require a query to be representable as a parse tree. In this work, we propose a unified architecture based on Sequence to Sequence models and Pointer Generator Network to handle both simple and complex queries. Unlike other works, our approach does not impose any restriction on the semantic parse schema. Furthermore, experiments show that it achieves state of the art performance on three publicly available datasets (ATIS, SNIPS, Facebook TOP), relatively improving between 3.3% and 7.7% in exact match accuracy over previous systems. Finally, we show the effectiveness of our approach on two internal datasets.